© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119220
    Prev
    Next
    INDEX
    Explanations

    time and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hasil
    -0.06
    boats
    -0.06
    そんな
    -0.06
     deshalb
    -0.06
     eigenvalue
    -0.05
     Malta
    -0.05
     세율
    -0.05
     そんな
    -0.05
     nila
    -0.05
     Iraqi
    -0.05
    POSITIVE LOGITS
     should
    0.07
     обязательно
    0.07
     include
    0.06
     where
    0.06
     debería
    0.06
    やはり
    0.06
     afore
    0.06
     Certainly
    0.06
    芻
    0.06
    communications
    0.06
    Activations Density 0.001%

    No Known Activations